Assessing large language models' accuracy in providing patient support for choroidal melanoma.

PURPOSE: This study aimed to evaluate the accuracy of information that patients can obtain from large language models (LLMs) when seeking answers to common questions about choroidal melanoma. METHODS: Comparative study comparing frequently asked questions from choroidal melanoma patients and queried three major LLMs-ChatGPT 3.5, Bing AI, and DocsGPT. Answers were reviewed by three ocular oncology experts and scored as accurate, partially accurate, or inaccurate. Statistical analysis compared the quality of responses across models. RESULTS: For medical advice questions, ChatGPT gave 92% accurate responses compared to 58% for Bing AI and DocsGPT. For pre/post-op questions, ChatGPT and Bing AI were 86% accurate while DocsGPT was 73% accurate. There were no statistically significant differences between models. ChatGPT responses were the longest while Bing AI responses were the shortest, but length did not affect accuracy. All LLMs appropriately directed patients to seek medical advice from professionals. CONCLUSION: LLMs show promising capability to address common choroidal melanoma patient questions at generally acceptable accuracy levels. However, inconsistent, and inaccurate responses do occur, highlighting the need for improved fine-tuning and oversight before integration into clinical practice.

Spontaneous suprachoroidal haemorrhage: clinical features, visual outcomes and prognosis factors.

BACKGROUND: To describe clinical features, risk factors and outcomes of patients with diagnosis of rare spontaneous suprachoroidal haemorrhage (SSCH) over a 20-year period from a tertiary eye unit. METHODS: Retrospective, observational case-series of patients with SSCH, defined as SCH without a known cause at diagnosis. Variables analysed included age, gender, ethnicity, systemic and ocular comorbidities, systemic medication, initial and final best corrected visual acuity (BCVA), clinical features, management and follow-up. RESULTS: Total of 11 eyes of 11 patients were identified. Median age was 70 years (SD 25.9). Most patients were female (82%) and white British. Median follow-up period was 2.2 years. Hypertension was the most frequently associated underlying systemic disease (45%) and 36% were on anti-coagulant or anti-platelet therapy. High myopia was observed in 36% of cases. Presenting BCVA of 1.00 logMAR or better was a positive predictor of final BCVA. No significant improvement in the initial versus final BCVA was found in patients who underwent surgery versus those who remained under observation. CONCLUSION: Patients over 60 years-old with hypertension, anticoagulant treatment, high myopia, and pseudophakia were common. Visual outcomes were poor, surgical intervention had limited impact. Good initial BCVA predicted better final acuity while extensive SSCH correlated with poorer visual results. Despite the study's limitations, this series offers valuable insights into visual prognosis and prognostic factors.

Analysis of optical coherence tomography biomarker probability detection in central serous chorioretinopathy by using an artificial intelligence-based biomarker detector.

AIM: To adopt a novel artificial intelligence (AI) optical coherence tomography (OCT)-based program to identify the presence of biomarkers associated with central serous chorioretinopathy (CSC) and whether these can differentiate between acute and chronic central serous chorioretinopathy (aCSC and cCSC). METHODS: Multicenter, observational study with a retrospective design enrolling treatment-naïve patients with aCSC and cCSC. The diagnosis of aCSC and cCSC was established with multimodal imaging and for the current study subsequent follow-up visits were also considered. Baseline OCTs were analyzed by an AI-based platform (Discovery® OCT Fluid and Biomarker Detector, RetinAI AG, Switzerland). This software allows to detect several different biomarkers in each single OCT scan, including subretinal fluid (SRF), intraretinal fluid (IRF), hyperreflective foci (HF) and flat irregular pigment epithelium detachment (FIPED). The presence of SRF was considered as a necessary inclusion criterion for performing biomarker analysis and OCT slabs without SRF presence were excluded from the analysis. RESULTS: Overall, 160 eyes of 144 patients with CSC were enrolled, out of which 100 (62.5%) eyes were diagnosed with cCSC and 60 eyes (34.5%) with aCSC. In the OCT slabs showing presence of SRF the presence of biomarkers was found to be clinically relevant (> 50%) for HF and FIPED in aCSC and cCSC. HF had an average percentage of 81% (± 20) in the cCSC group and 81% (± 15) in the aCSC group (p = 0.4295) and FIPED had a mean percentage of 88% (± 18) in cCSC vs. 89% (± 15) in the aCSC (p = 0.3197). CONCLUSION: We demonstrate that HF and FIPED are OCT biomarkers positively associated with CSC when present at baseline. While both HF and FIPED biomarkers could aid in CSC diagnosis, they could not distinguish between aCSC and cCSC at the first visit. AI-assisted biomarker detection shows promise for reducing invasive imaging needs, but further validation through longitudinal studies is needed.

Enabling People With Intellectual and Sensory Disabilities to Trigger a Tablet's Delivery of Task Instructions by Walking to the Tablet: Proof-of-Concept Study.

BACKGROUND: People with intellectual and sensory or sensory-motor disabilities tend to have problems performing multistep tasks. To alleviate their problems, technological solutions have been developed that provide task-step instructions. Instructions are generally delivered at people's request (eg, as they touch an area of a computer or tablet screen) or automatically, at preset intervals. OBJECTIVE: This study carried out a preliminary assessment of a new tablet-based technology system that presented task-step instructions when participants with intellectual and sensory disabilities walked close to the tablet (ie, did not require participants to perform fine motor responses on the tablet screen). METHODS: The system entailed a tablet and a wireless camera and was programmed to present instructions when participants approached the tablet, that is, when the camera positioned in front of the tablet detected them. Two instructions were available for each task step. One instruction concerned the object(s) that the participants were to collect, and the other instruction concerned the "where" and "how" the object(s) collected would need to be used. For 3 of the six participants, the two instructions were presented in succession, with the second instruction presented once the required object(s) had been collected. For the other 3 participants, the two instructions were presented simultaneously. Instructions consisted of pictorial representations combined with brief verbal phrases. The impact of the system was assessed for each of the 2 groups of participants using a nonconcurrent multiple baseline design across individuals. RESULTS: All participants were successful in using the system. Their mean frequency of correct task steps was close to or above 11.5 for tasks including 12 steps. Their level of correct performance tended to be much lower during the baseline phase when they were to receive the task-step instructions from a regular tablet through scrolling responses. CONCLUSIONS: The findings, which need to be interpreted with caution given the preliminary nature of the study, suggest that the new tablet-based technology system might be useful for helping people with intellectual and sensory disabilities perform multistep tasks.

Perspectives on the currently available pharmacotherapy for wet macular degeneration.

INTRODUCTION: Wet age-related macular degeneration (w-AMD) is a leading cause of visual impairment globally, with its prevalence expected to rise alongside increasing life expectancy. The current standard treatment involves frequent intravitreal injections of anti-VEGF agents, which although revolutionary, pose significant burdens on both patients and healthcare services. AREAS COVERED: This review explores current and emerging pharmaceutical treatments for w-AMD, focusing on their pharmacokinetics, pharmacodynamics, efficacy, and safety. Promising developments include extending treatment intervals with newer anti-VEGF agents like brolucizumab and faricimab, biosimilars offering cost-effective options, and exploring innovative drug delivery methods such as subretinal gene therapy. Combination therapies, gene therapies, and novel agents like KSI-301 and OPT-302 show potential for improving treatment outcomes and reducing treatment burden. EXPERT OPINION: While current treatments for w-AMD have significantly advanced with the advent of anti-VEGF therapies, their limitations in terms of treatment burden and incomplete responses have spurred research into diverse alternative approaches. These innovative strategies offer hope for improving patient outcomes and reducing healthcare burdens, suggesting a promising future for w-AMD management.

Iris Reconstruction: A Surgeon's Guide.

Objectives: The aim of this review paper is to summarise surgical options available for repairing iris defects at the iris-lens plane, focusing on suturing techniques, iridodialysis repair, and prosthetic iris devices. Methods: A thorough literature search was conducted using multiple databases, including Medline, PubMed, Web of Science Core Collection, and the Cochrane Library, from inception to February 2024. Relevant studies were screened based on predefined criteria, and primary references cited in selected articles were also reviewed. Results: Various surgical techniques were identified for iris defect repair. Suturing methods such as interrupted full-thickness sutures and the McCannel technique offer solutions for smaller defects, while iridodialysis repair techniques address detachment of the iris from the ciliary body. Prosthetic iris devices, including iris-lens diaphragm devices, endocapsular capsular tension ring-based devices, and customizable artificial iris implants, provide options for larger defects, each with its own advantages and limitations. Conclusions: Successful iris reconstruction requires a personalised approach considering factors like defect size, ocular comorbidities, and patient preference. Surgeons must possess a thorough understanding of available techniques and prosthetic devices to achieve optimal outcomes in terms of both visual function and, nonetheless, cosmetic appearance.

Prediction of chronic central serous chorioretinopathy through combined manual annotation and AI-assisted volume measurement of flat irregular pigment epithelium.

INTRODUCTION: The aim of this study is to investigate the role of an artificial intelligence (AI)-developed OCT program to predict the clinical course of central serous chorioretinopathy (CSC ) based on baseline pigment epithelium detachment (PED) features. METHODS: Single-center, observational study with a retrospective design. Treatment-naïve patients with acute CSC and chronic CSC were recruited and OCTs were analyzed by an AI-developed platform (Discovery OCT Fluid and Biomarker Detector, RetinAI AG, Switzerland), providing automatic detection and volumetric quantification of PEDs. Flat irregular PED presence was annotated manually and afterwards measured by the AI program automatically. RESULTS: 115 eyes of 101 patients with CSC were included, of which 70 were diagnosed with chronic CSC and 45 with acute CSC. It was found that patients with baseline presence of foveal flat PEDs and multiple flat foveal and extrafoveal PEDs had a higher chance of developing chronic form. AI-based volumetric analysis revealed no significant differences between the groups. CONCLUSIONS: While more evidence is needed to confirm the effectiveness of AI-based PED quantitative analysis, this study highlights the significance of identifying flat irregular PEDs at the earliest stage possible in patients with CSC, to optimize patient management and long-term visual outcomes.

Proliferative vitreoretinopathy: an update on the current and emerging treatment options.

Proliferative vitreoretinopathy (PVR) remains the main cause of failure in retinal detachment (RD) surgery and a demanding challenge for vitreoretinal surgeons. Despite the large improvements in surgical techniques and a better understanding of PVR pathogenesis in the last years, satisfactory anatomical and visual outcomes have not been provided yet. For this reason, several different adjunctive pharmacological agents have been investigated in combination with surgery. In this review, we analyze the current and emerging adjunctive treatment options for the management of PVR and we discuss their possible clinical application and beneficial role in this subgroup of patients.

BASELINE SPECTRAL DOMAIN OPTICAL COHERENCE TOMOGRAPHIC RETINAL LAYER FEATURES IDENTIFIED BY ARTIFICIAL INTELLIGENCE PREDICT THE COURSE OF CENTRAL SEROUS CHORIORETINOPATHY.

PURPOSE: To identify optical coherence tomography (OCT) features to predict the course of central serous chorioretinopathy (CSC) with an artificial intelligence-based program. METHODS: Multicenter, observational study with a retrospective design. Treatment-naïve patients with acute CSC and chronic CSC were enrolled. Baseline OCTs were examined by an artificial intelligence-developed platform (Discovery OCT Fluid and Biomarker Detector, RetinAI AG, Switzerland). Through this platform, automated retinal layer thicknesses and volumes, including intaretinal and subretinal fluid, and pigment epithelium detachment were measured. Baseline OCT features were compared between acute CSC and chronic CSC patients. RESULTS: One hundred and sixty eyes of 144 patients with CSC were enrolled, of which 100 had chronic CSC and 60 acute CSC. Retinal layer analysis of baseline OCT scans showed that the inner nuclear layer, the outer nuclear layer, and the photoreceptor-retinal pigmented epithelium complex were significantly thicker at baseline in eyes with acute CSC in comparison with those with chronic CSC ( P < 0.001). Similarly, choriocapillaris and choroidal stroma and retinal thickness (RT) were thicker in acute CSC than chronic CSC eyes ( P = 0.001). Volume analysis revealed average greater subretinal fluid volumes in the acute CSC group in comparison with chronic CSC ( P = 0.041). CONCLUSION: Optical coherence tomography features may be helpful to predict the clinical course of CSC. The baseline presence of an increased thickness in the outer retinal layers, choriocapillaris and choroidal stroma, and subretinal fluid volume seems to be associated with acute course of the disease.

Prechoroidal Cleft Regression After Switch to Intravitreal Brolucizumab.

INTRODUCTION: Prechoroidal cleft has been described as a negative prognostic biomarker in patients affected with neovascular age related macular degeneration (nAMD). This peculiar finding consists of a lenticular hyporeflective space located between an outward bowing of Bruch's membrane and the base of a fibrovascular retinal pigment epithelium detachment (PED). Previous studies have reported the partial or complete regression of prechoroidal clefts after treatment with anti-vascular endothelial growth factor (VEGF) injections. CASE REPORT: To report a case of complete anatomical regression of an unresponsive prechoroidal cleft after switching to intravitreal Brolucizumab. The patient maintained cleft regression over time and no adverse events (i.e., RPE tears, intraocular inflammation) were observed during follow-up. CONCLUSIONS AND IMPORTANCE: To our knowledge, this case report is the first to analyze the clinical efficacy of brolucizumab targeting prechoroidal clefts. Clinical implication and pathogenesis of prechoroidal clefts are yet to be fully elucidated.

"Application and accuracy of artificial intelligence-derived large language models in patients with age related macular degeneration".

INTRODUCTION: Age-related macular degeneration (AMD) affects millions of people globally, leading to a surge in online research of putative diagnoses, causing potential misinformation and anxiety in patients and their parents. This study explores the efficacy of artificial intelligence-derived large language models (LLMs) like in addressing AMD patients' questions. METHODS: ChatGPT 3.5 (2023), Bing AI (2023), and Google Bard (2023) were adopted as LLMs. Patients' questions were subdivided in two question categories, (a) general medical advice and (b) pre- and post-intravitreal injection advice and classified as (1) accurate and sufficient (2) partially accurate but sufficient and (3) inaccurate and not sufficient. Non-parametric test has been done to compare the means between the 3 LLMs scores and also an analysis of variance and reliability tests were performed among the 3 groups. RESULTS: In category a) of questions, the average score was 1.20 (± 0.41) with ChatGPT 3.5, 1.60 (± 0.63) with Bing AI and 1.60 (± 0.73) with Google Bard, showing no significant differences among the 3 groups (p = 0.129). The average score in category b was 1.07 (± 0.27) with ChatGPT 3.5, 1.69 (± 0.63) with Bing AI and 1.38 (± 0.63) with Google Bard, showing a significant difference among the 3 groups (p = 0.0042). Reliability statistics showed Chronbach's α of 0.237 (range 0.448, 0.096-0.544). CONCLUSION: ChatGPT 3.5 consistently offered the most accurate and satisfactory responses, particularly with technical queries. While LLMs displayed promise in providing precise information about AMD; however, further improvements are needed especially in more technical questions.

Investigational drugs inhibiting complement for the treatment of geographic atrophy.

INTRODUCTION: Geographic atrophy (GA) is a progressive form of age-related macular degeneration (AMD) that leads to severe visual impairment and central vision loss. Traditional treatment options for GA are limited, highlighting the need for new therapeutic approaches. In recent years, targeting the complement system has emerged as a promising strategy for the treatment of GA. AREAS COVERED: This expert opinion article reviews the investigational drugs inhibiting the complement cascade for the treatment of GA. Specifically, it focuses on the recent FDA approved pegcetacoplan, a C3 complement inhibitor, and avacincaptad pegol, a C5 complement inhibitor, highlighting their potential efficacy and safety profiles based on clinical trial data. EXPERT OPINION: FDA approval of intravitreal pegcetacoplan and avacincaptad pegol marks significant progress in the landscape of GA treatment. However, variable results from trials underscore the complex nature of GA and the importance of patient selection. Complement inhibition holds promise, but ongoing research is vital to refine treatment strategies and offer improved outcomes for GA patients.

Available Assistive Technology Outcome Measures: Systematic Review.

BACKGROUND: The World Health Organization claimed that measuring outcomes is necessary to understand the benefits of assistive technology (AT) and create evidence-based policies and systems to ensure universal access to it. In clinical practice, there is an increasing need for standardized methods to track AT interventions using outcome assessments. OBJECTIVE: This review provides an overview of the available outcome measures that can be used at the follow-up stage of any AT intervention and integrated into daily clinical or service practice. METHODS: We systematically searched for original manuscripts regarding available and used AT outcome measures by searching for titles and abstracts in the PubMed, Scopus, and Web of Science databases up to March 2023. RESULTS: We analyzed 955 articles, of which 50 (5.2%) were included in the review. Within these, 53 instruments have been mentioned and used to provide an AT outcome assessment. The most widely used tool is the Quebec User Evaluation of Satisfaction with Assistive Technology, followed by the Psychosocial Impact of Assistive Technology Scale. Moreover, the identified measures addressed 8 AT outcome domains: functional efficacy, satisfaction, psychosocial impact, caregiver burden, quality of life, participation, confidence, and usability. The AT category Assistive products for activities and participation relating to personal mobility and transportation was the most involved in the reviewed articles. CONCLUSIONS: Among the 53 cited instruments, only 17 (32%) scales were designed to evaluate specifically assistive devices. Moreover, 64% (34/53) of the instruments were only mentioned once to denote poor uniformity and concordance in the instruments to be used, limiting the possibility of comparing the results of studies. This work could represent a good guide for promoting the use of validated AT outcome measures in clinical practice that can be helpful to AT assessment teams in their everyday activities and the improvement of clinical practice.

Using a Social Robot to Engage Older Adults Living in Residential Care Homes in Cognitive Training: Preliminary Results from the SHAPES Project.

The employment of socially assistive robotics (SAR) is increasingly being considered a credible solution to support healthcare systems in dealing with an aging society. In this contribution, we explore the experience of older adults (n = 11) living in a residential facility with a cognitive training intervention conducted with the support of a SAR. Within the HORIZON2020 Project SHAPES, a mixed-method study has been conducted to collect preliminary evidence on users' engagement and acceptance of the proposed SAR-based intervention. The results suggest that the SAR-based cognitive training intervention conducted was accepted by all stakeholders. Data on enjoyment of participants indicate that users did not experience a "novelty effect" of the proposed innovation, but longer sessions are needed to confirm this result.

I'm in Tales MOOC on Tangible User Interfaces and the UDL Model: A Case Study Design.

This paper presents the design and implementation of a Massive Open Online Course (MOOC) developed on Universal Design for Learning (UDL) principles within the I'm in Tales Erasmus Project, focused on Tangible User Interfaces (TUIs) and their potential in enhancing storytelling for inclusive education. The MOOC aims to equip educators with the knowledge and skills necessary to design and implement TUIs in educational settings, promoting their understanding of TUIs as tools for creating accessible and engaging storytelling experiences for all learners. The course follows a self-paced and independent learning approach, incorporating active, contextual, social, and reflective learning methods. Preliminary evaluation results are discussed, and further evaluation methods are planned to assess the MOOC's impact on educators' understanding of TUIs and their potential for inclusive education. The use case presented illustrates the practical application of TUIs in universally designed learning experiences. The study concludes that the MOOC provides a valuable resource for educators and learners interested in TUIs and their role in enhancing inclusive education.

'Touching' Stories: Towards the Development of Tangible User Interfaces Story-Building Authoring Tool for Inclusive Education.

Tangible User Interfaces (hereafter, TUIs) are novel forms of human-computer interactions based on the physical manipulation of any kind of object/artifact. A great potential of TUIs technologies is the possibility to personalize objects and interaction between the user and the system. The high level of platform flexibility allows, for example, a multisensory approach, that is crucial for children that have sensory limitations and disabilities. This contribution aims at presenting and discussing the development of an authoring tool for creating TUI-supported activities for inclusive digital storytelling. The authoring tool is a product of collaboration and consultation with researchers and teachers involved in the ERASMUS+ project I'M IN TALES. A preliminary usability validation study using a mixed-method approach has been conducted involving 50 educators and assistive technology professionals. The results indicate an overall acceptance of the system. The feedback provided by the participants involved will be used for the future refinement of the tool.

Faricimab for the Treatment of Diabetic Macular Edema and Neovascular Age-Related Macular Degeneration.

Nowadays; intravitreal anti-vascular endothelial growth factor (VEGF) drugs are considered the first-line therapeutic strategy for treating macular exudative diseases; including wet age-related macular degeneration (w-AMD) and diabetic macular edema (DME). Despite the important clinical achievements obtained by anti-VEGF drugs in the management of w-AMD and DME; some limits still remain; including high treatment burden; the presence of unsatisfactory results in a certain percentage of patients and long-term visual acuity decline due to complications such as macular atrophy and fibrosis. Targeting the angiopoietin/Tie (Ang/Tie) pathway beyond the VEGF pathway may be a possible therapeutic strategy; which may has the potential to solve some of the previous mentioned challenges. Faricimab is a new; bispecific antibody targeting both VEGF-A and the Ang-Tie/pathway. It was approved by FDA and; more recently; by EMA for treating w-AMD and DME. Results from phase III trials TENAYA and LUCERNE (w-AMD) and RHINE and YOSEMITE (DME) have shown the potential of faricimab to maintain clinical efficacy with more prolonged treatment regimens compared to aflibercept (12 or 16 weeks) with a a good safety profile.

Low-Cost Technology-Aided Programs for Supporting People With Motor, Visual, and Intellectual Disabilities in Functional Forms of Occupation and Communication: Proof-of-Concept Study.

BACKGROUND: People with motor, visual, and intellectual disabilities may have serious problems in independently accessing various forms of functional daily occupation and communication. OBJECTIVE: The study was aimed at developing and assessing new, low-cost technology-aided programs to help people with motor or visual-motor and intellectual disabilities independently engage in functional forms of occupation and communication with distant partners. METHODS: Two programs were set up using a smartphone interfaced with a 2-switch device and a tablet interfaced with 2 pressure sensors, respectively. Single-subject research designs were used to assess (1) the first program with 2 participants who were blind, had moderate hand control, and were interested in communicating with distant partners through voice messages; and (2) the second program with 2 participants who possessed functional vision, had no or poor hand control, and were interested in communicating with their partners through video calls. Both programs also supported 2 forms of occupational engagement, that is, choosing and accessing preferred leisure events consisting of songs and music videos, and listening to brief stories about relevant daily topics and answering questions related to those stories. RESULTS: During the baseline phase (when only a conventional smartphone or tablet was available), 2 participants managed sporadic access to leisure or leisure and communication events. The other 2 participants did not show any independent leisure or communication engagement. During the intervention (when the technology-aided programs were used), all participants managed to independently engage in multiple leisure and communication events throughout the sessions and to listen to stories and answer story-related questions. CONCLUSIONS: The findings, which need to be interpreted with caution given the nature of the study and the small number of participants, seem to suggest that the new programs may be viable tools for helping people with motor or visual-motor and intellectual disabilities independently access leisure, communication, and other forms of functional engagement.